Scene Categorization From Contours: Medial Axis Based Salience Measures

Morteza Rezanejad, Gabriel Downs, John Wilder, Dirk B. Walther, Allan Jepson, Sven Dickinson, Kaleem Siddiqi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4116-4124

Abstract


The computer vision community has witnessed recent advances in scene categorization from images, with the state of the art systems now achieving impressive recognition rates on challenging benchmarks. Such systems have been trained on photographs which include color, texture and shading cues. The geometry of shapes and surfaces, as conveyed by scene contours, is not explicitly considered for this task. Remarkably, humans can accurately recognize natural scenes from line drawings, which consist solely of contour-based shape cues. Here we report the first computer vision study on scene categorization of line drawings derived from popular databases including an artist scene database, MIT67 and Places365. Specifically, we use off-the-shelf pre-trained Convolutional Neural Networks (CNNs) to perform scene classification given only contour information as input, and find performance levels well above chance. We also show that medial-axis based contour salience methods can be used to select more informative subsets of contour pixels, and that the variation in CNN classification performance on various choices for these subsets is qualitatively similar to that observed in human performance. Moreover, when the salience measures are used to weight the contours, we find that these weights boost our CNN performance above that for unweighted contour input. That is, the medial axis based salience weights appear to add useful information that is not available when CNNs are trained to use contours alone.

Related Material


[pdf]
[bibtex]
@InProceedings{Rezanejad_2019_CVPR,
author = {Rezanejad, Morteza and Downs, Gabriel and Wilder, John and Walther, Dirk B. and Jepson, Allan and Dickinson, Sven and Siddiqi, Kaleem},
title = {Scene Categorization From Contours: Medial Axis Based Salience Measures},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}